Spaces:
Sleeping
Sleeping
| import os | |
| import streamlit as st | |
| from st_aggrid import AgGrid | |
| import pandas as pd | |
| from transformers import pipeline, T5ForConditionalGeneration, T5Tokenizer | |
| # Set the page layout for Streamlit | |
| st.set_page_config(layout="wide") | |
| # CSS styling | |
| # ... (keep your existing CSS code) | |
| # Initialize TAPAS pipeline | |
| tqa = pipeline(task="table-question-answering", | |
| model="google/tapas-large-finetuned-wtq", | |
| device="cpu") | |
| # Initialize T5 tokenizer and model for text generation | |
| t5_tokenizer = T5Tokenizer.from_pretrained("t5-small") | |
| t5_model = T5ForConditionalGeneration.from_pretrained("t5-small") | |
| # File uploader in the sidebar | |
| file_name = st.sidebar.file_uploader("Upload file:", type=['csv', 'xlsx']) | |
| # File processing and question answering | |
| if file_name is None: | |
| st.markdown('<p class="font">Please upload an excel or csv file </p>', unsafe_allow_html=True) | |
| else: | |
| try: | |
| # Check file type and handle reading accordingly | |
| if file_name.name.endswith('.csv'): | |
| df = pd.read_csv(file_name, sep=';', encoding='ISO-8859-1') # Adjust encoding if needed | |
| elif file_name.name.endswith('.xlsx'): | |
| df = pd.read_excel(file_name, engine='openpyxl') # Use openpyxl to read .xlsx files | |
| else: | |
| st.error("Unsupported file type") | |
| df = None | |
| if df is not None: | |
| numeric_columns = df.select_dtypes(include=['object']).columns | |
| for col in numeric_columns: | |
| df[col] = pd.to_numeric(df[col], errors='ignore') | |
| st.write("Original Data:") | |
| st.write(df) | |
| df_numeric = df.copy() | |
| df = df.astype(str) | |
| # Display the first 5 rows of the dataframe in an editable grid | |
| grid_response = AgGrid( | |
| df.head(5), | |
| columns_auto_size_mode='FIT_CONTENTS', | |
| editable=True, | |
| height=300, | |
| width='100%', | |
| ) | |
| except Exception as e: | |
| st.error(f"Error reading file: {str(e)}") | |
| # User input for the question | |
| question = st.text_input('Type your question') | |
| # Process the answer using TAPAS and T5 | |
| with st.spinner(): | |
| if st.button('Answer'): | |
| try: | |
| raw_answer = tqa(table=df, query=question, truncation=True) | |
| st.markdown("<p style='font-family:sans-serif;font-size: 0.9rem;'> Raw Result From TAPAS: </p>", | |
| unsafe_allow_html=True) | |
| st.success(raw_answer) | |
| answer = raw_answer['answer'] | |
| aggregator = raw_answer.get('aggregator', '') | |
| coordinates = raw_answer.get('coordinates', []) | |
| cells = raw_answer.get('cells', []) | |
| if aggregator == 'SUM': | |
| # Convert cell values to numbers and sum them | |
| values = [float(cell) for cell in cells if cell.replace('.', '').isdigit()] | |
| total_sum = sum(values) | |
| base_sentence = f"The sum for '{question}' is {total_sum}." | |
| else: | |
| # Construct a base sentence for other aggregators or no aggregation | |
| base_sentence = f"The answer from TAPAS for '{question}' is {answer}." | |
| if coordinates and cells: | |
| rows_info = [f"Row {coordinate[0] + 1}, Column '{df.columns[coordinate[1]]}' with value {cell}" | |
| for coordinate, cell in zip(coordinates, cells)] | |
| rows_description = " and ".join(rows_info) | |
| base_sentence += f" This includes the following data: |